CALL FOR PAPERS

SIGIR 2011 Workshop on Internet Advertising (IA2011)
July 28, 2011
Beijing, China

http://research.microsoft.com/~ia2011

IMPORTANT DATES

Submission deadline: June 20, 2011
Notification of Acceptance: July 10, 2011
Camera ready: July 18, 2011
Workshop Date: July 28, 2011

OVERVIEW

Digital online advertising is a form of promotion that uses the Internet and World Wide Web for the express purpose of delivering marketing messages to attract customers. Examples of online advertising include text ads that appear on search engine results pages, banner ads, in-text ads, or Rich Media ads that appear on regular web pages, portals, or applications. Over the past 15 years online advertising, a $65 billion industry worldwide in 2009, has leveraged many key results in information science such as indexing, learning to rank, personalization, geographic information systems, graph-based algorithms, and many others. We already find ourselves in the third generation of online advertising.
1. The first generation largely borrowed techniques and business models from offline advertising;
2. The second generation is characterized by the introduction and use of purposed-built business models for online advertising, the use data analytics and optimization engines;
3. While the third generation (which began around 2007) has largely been driven by a focus on personalization that has been enabled by new data sources, social networks, mobile-based connectivity, and by advances in the fields of information retrieval, machine learning, statistics, distributed computing, optimization and economics.

That being said, the field of information retrieval has been equally revolutionized by digital advertising with its insatiable need for even more fine-grained targeting, milli-second turnarounds times, peta-byte-based analytics, accurate segmentation and forecasting. These and other areas have and continue to push the theories and algorithms of information retrieval.

The enormous success of deploying IR approaches and the huge demand to build ever more efficient and effective digital advertising systems presents a great opportunity along with posing great challenges to the information retrieval community. It calls for new theories and technologies to be developed. Internet advertising is a complex problem. It has different formats, including search advertising, display advertising, social network advertising, in app/game advertising). It contains multiple parties (i.e., advertisers, users, publishers, and ad platforms such as ad exchanges), which interact with each other harmoniously but exhibit a conflict of interest when it comes to risk and revenue objectives. It is highly dynamic in terms of the rapid change of user information needs, non-stationary bids of advertisers, and the frequent modifications of ads campaigns. It is very large scale, with billions of keywords, tens of millions of ads, billions of users, millions of advertisers where events such as clicks and actions can be extremely rare. In addition, the field lies at intersection of information retrieval, machine learning, economics, optimization, distributed systems and information science all very advanced and complex fields in their own right.

For such a complex problem, conventional technologies and evaluation methodologies are not sufficient, and the development of new algorithms and theories is sorely needed.

The goal of this workshop is bring together both practitioners and academics in the field of digital advertising to overview the state of the art in Internet advertising from an information scientist’s perspective, and to discuss future directions and challenges in research and development. We expect the workshop to help develop a community of researchers who are interested in this area, and yield future collaboration and exchanges.

Possible topics include:

IR and advertising
1. CTR prediction
2. Relevancy studies for advertising
3. Behavior targeting and audience selection
4. Ad selection and ranking
5. Ad taxonomy construction and alignment
6. Ad classification and clustering
Evaluation and benchmarks
1. Human labeling for ads
2. Evaluation metrics for ad effectiveness
3. Public benchmarks for academic research
4. Offline simulation
5. Online experimental design (considering second order effects)
Beyond traditional advertising
1. In game advertising
2. In app advertising
3. Mobile advertising
4. Social advertising
5. Advertising on four screens
6. Ad Exchanges and RTB: expressing constraints and forecasting
7. Personalization
Others
1. Credit assignment
2. Privacy protection
3. Auction theory and mechanism design
4. Bid and campaign optimization


The above list is not exhaustive, and we welcome submissions on highly related topics too.



WORKSHOP FORMAT

Broadly, this one-day workshop aims at exploring the current challenges in Internet advertising. It will explore these topics in tutorials and invited talks.
In addition, we will have a poster session with spotlight presentations to provide a platform for presenting new contributions.


SUBMISSION DETAILS

Submissions to the IA workshop should be in the format of short papers: 4-6 pages formatted in the SIGIR style.
The submission does not need to be blind. Please upload submissions in PDF to https://cmt.research.microsoft.com/ia2011/.
Accepted papers will be made available Internet at the workshop website. In addition, we plan to invite extended versions of selected papers for a special issue of a top-tier information retrieval journal (under discussion).


ORGANIZING COMMITTEE

-- Tie-Yan Liu (Microsoft Research Asia)
-- Tao Qin (Microsoft Research Asia)
-- James G. Shanahan (Independent Consultant)


CONTACT

Jimi Shanahan: James_DOT_Shanahan_AT_gmail_DOT_com